AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

Domain Sensitive Federated Learning with Fisher-Informed Pruning

Chenchen Lin, Wenhao Yuan, Zhengji Xu, Xuehe Wang

CVPR 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add DSFP, DSR and SA modules (ablation)FedFIP baseline · Digitsavg accuracy: 74.35 -> 76.48Improved
add DSFP, DSR and SA modules (ablation)FedFIP baseline · Office-Caltechavg accuracy: 55.39 -> 64.44Improved
add DSFP, DSR and SA modules (ablation)FedFIP baseline · PACSavg accuracy: 77.89 -> 82.02Improved
add domain-sensitive Fisher pruning alone (ablation)no-module baseline · Office-Caltechavg accuracy: 55.39 -> 58.78Improved
increase global sparsity ratio from 0.2 to 0.6 (ablation)FedFIP · Digitsavg accuracy: 57.58 -> 71.99Improved
increase global sparsity ratio from 0.6 to 0.8 (ablation)FedFIP · Digitsavg accuracy: 71.99 -> 74.44Improved
use ResNet-50 instead of ResNet-18 (ablation)FedFIP · Office-Caltechavg accuracy: 64.44 -> 65.86Improved
use ResNet-10 instead of ResNet-18 (ablation)FedFIP · Digitsavg accuracy: 76.48 -> 75.52Hurt
raise local importance threshold phi (ablation)FedFIP · Digits and Office-CaltechaccuracyHurt
use overly strong contrastive regularization (ablation)FedFIP · Digits and Office-CaltechaccuracyHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy